In brain-machine interface (BMI) prosthetic systems, recordings of brain activity are used to control external devices such as computers or robots. BMI systems that have shown the highest fidelity of control use neural signals recorded directly from microelectrodes in the brain to control upper-limb prostheses. These have progressed from allowing control of 2 and 3 dimensional movement of a cursor on a computer screen [1], [2] to control of robot arms in first four [3], [4] and more recently seven degrees-of-freedom (DoF) (Fig. 1) [5], [6]. These types of systems require methods to train users to control large numbers of DoF simultaneously. In this paper we present a new method for shared-control guidance. This method of "Positive-Span" Virtual Fixturing extends the concept of Virtual Fixtures to guide both translational and rotational DoF of a brain-controlled robot hand toward whole sets of robot poses that would allow an object to be grasped. This system was used to successfully train monkeys to operate the 7-DoF BMI [5], leading directly to the simplified system of "ortho-impedance" used to guide human subject BMI control in a similar experiment [6].

The new field of location proteomics seeks to provide a comprehensive, objective characterization of the subcellular locations of all proteins expressed in a given cell type. Previous work has demonstrated that automated classifiers can recognize the patterns of all major subcellular organelles and structures in fluorescence microscope images with high accuracy. However, since some proteins may be present in more than one organelle, this paper addresses a more difficult task: recognizing a pattern that is a mixture of two or more fundamental patterns. The approach utilizes an object-based image model, in which each image of a location pattern is represented by a set of objects of distinct, learned types. Using a two-stage approach in which object types are learned and then cell-level features are calculated based on the object types, the basic location patterns were well recognized. Given the object types, a multinomial mixture model was built to recognize mixture patterns. Under appropriate conditions, synthetic mixture patterns can be decomposed with over 80% accuracy, which, for the first time, shows that the problem of computationally decomposing subcellular patterns into fundamental organelle patterns can be solved.

There is extensive interest in automating the collection, organization and analysis of biological data. Data in the form of images present special challenges for such efforts. Since fluorescence microscope images are a primary source of information about the location of proteins within cells, we have set as a long-term goal the building of a knowledge base system that can interpret such images in online journals. To this end, we first developed a robot that searches online journals and finds fluorescence microscope images of individual cells. We then characterized the applicability of pattern classification methods we have previously used on images obtained under controlled conditions to images from different sources and to images subjected to manipulations commonly performed during publication. The results indicate the feasibility of developing search engines to find fluorescence microscope images depicting particular subcellular patterns.